Research map / Vision-language and multimodal / CLIP and zero-shot
InstructHOI: Context-Aware Instruction for Multi-Modal Reasoning in Human-Object Interaction Detection
Jinguo Luo, Weihong Ren, Quanlong Zheng, Yanhao Zhang, Zhenlong Yuan, Zhiyong Wang, Haonan Lu, Honghai LIU
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes InstructHOI, an instruction-based approach that uses context-aware instructions to guide multi-modal reasoning for human-object interaction detection with large foundation models.
Problem
Human-object interaction (HOI) detection built on large foundation models (CLIP, GPT) typically relies on single- or multi-modal prompts, which focus on transferring HOI-specific knowledge rather than reasoning over context.
Approach
Replaces fixed prompts with context-aware instructions that drive multi-modal reasoning over pretrained foundation models for HOI detection; the abstract only partially describes the method.
Closest papers by meaning
- Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild (ECCV 2026 · similarity 0.93)
- Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection (ICCV 2023 · similarity 0.92)
- Open-World Human-Object Interaction Detection via Multi-modal Prompts (CVPR 2024 · similarity 0.90)
- ContextHOI: Spatial Context Learning for Human-Object Interaction Detection (AAAI 2025 · similarity 0.89)
- Discovering Syntactic Interaction Clues for Human-Object Interaction Detection (CVPR 2024 · similarity 0.89)
- HOIMamba: Efficient Mamba-based Disentangled Progressive Learning for HOI Detection (AAAI 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
